Developer Tools & APIs
APIs, SDKs, MCP, IDEs, developer platforms, and technical migration updates.
OpenAI opens the Agents API in public beta: giving every developer the same managed harness that powers Codex
The Agents API public beta lets developers spin up long-running cloud agents using OpenAI's own orchestration infrastructure, at no extra fee.
Claude Code sets Fable 5.1 as default model and adds a fullscreen diff panel
Claude Code v2.1.257 makes Fable 5.1 the default model, adds a live /diff panel, surfaces headless commands, and fixes a batch of bugs.
Google sets 30 September 2026 deadline to drop gemini-omni-flash-preview
Google deprecates gemini-omni-flash-preview on 30 September 2026. Teams must migrate to the GA gemini-omni-1.1-flash endpoint before that date.
Google is shutting down gemini-robotics-er-1.6-preview on 31 August 2026
Google retires gemini-robotics-er-1.6-preview on 31 August 2026. The replacement, gemini-robotics-er-2-preview, adds multi-robot coordination and agentic code execution.
GPT-5.4 and GPT-5.4 mini are now retired from Codex for ChatGPT-authenticated users
From 31 August 2026, GPT-5.4 and GPT-5.4 mini no longer work in Codex under ChatGPT sign-in. Here is what to do.
Anthropic makes Claude Sonnet 5's $2/$10 pricing permanent, cancels September price hike
Anthropic has confirmed the $2/$10 per million token rate for Claude Sonnet 5 is now permanent. The planned 50% increase from 1 September 2026 will not happen.
Claude Code's 29 August update: faster startup, a much smaller Linux download, and better token visibility
Claude Code now starts before the sandbox loads, the Linux binary shrinks from ~340 MB to ~75 MB, and /cost, /usage, and /tasks get per-command token detail.
Claude Code v2.1.248 adds restricted mode for safe CI/CD use and expands multi-agent messaging to enterprise clouds
Claude Code v2.1.248 ships a restricted mode for CI pipelines, widens cross-session agent messaging to Bedrock, Vertex, and Foundry, and adds per-agent prompt cache TTL.
Claude Code v2.1.243 adds loop token visibility, curated model picker, contracted pricing, and granular prompt-cache controls
Claude Code v2.1.243 ships four developer-facing additions: loop token breakdowns, modelPicker curation, contracted modelPricing, and split prompt-cache TTLs.
Claude 3 Haiku on Vertex AI is now shut down: here's what to do if your app is broken
Anthropic's Claude 3 Haiku on Vertex AI reached end-of-life on 23 August 2026. Any app still calling it will now receive errors.
Two OpenAI shutdowns land on 26 August 2026: o3 leaves ChatGPT and the Assistants API is gone for good
On 26 August 2026, OpenAI removes o3 from ChatGPT's model picker and permanently shuts down the Assistants API. Here's what breaks and what to do.
Claude Files API graduates to general availability
The Files API beta header is no longer required on /v1/files endpoints, simplifying file-grounded Claude API integrations from 20 August 2026.
Grok 4.1 Fast models are being shut down on the Gemini Enterprise Agent Platform on 20 August 2026
The xai/grok-4.1-fast-reasoning and xai/grok-4.1-fast-non-reasoning model IDs stop working on 20 August 2026. Here's how to migrate.
Gemini image-generation model shutdown: what to do if your app is broken on 17 August 2026
Three Imagen 4 API endpoints shut down permanently on 17 August 2026. Here's what broke, why, and how to migrate to gemini-3.1-flash-image.
Anthropic shuts down legacy Claude Workbench and three experimental API endpoints on 17 August 2026
The legacy Claude Workbench and three /v1/experimental/ prompt API endpoints reach end of life on 17 August 2026. Here's what to do.
Claude Code v2.1.233: GitLab MR support, per-user spend attribution, and Linux memory limits for Bash
Claude Code v2.1.233 adds GitLab MR URL support, opt-in per-user identity forwarding, Linux memory cgroup limits, and a configurable WebFetch cache TTL.
Codex gets portable Agent Plugins, MCP 2026-07-28 support, and Bedrock caching
Codex v0.147.0 ships portable Agent Plugins with cross-catalog search, the latest MCP spec, Amazon Bedrock caching, and smarter approval workflows.
Sign in with ChatGPT: OpenAI launches its first cross-platform identity system
OpenAI's 'Sign in with ChatGPT' beta lets users authenticate into Airtable, GitLab, HubSpot, Notion, Supabase, and Vercel directly from ChatGPT.
Anthropic removes fast mode from Claude Opus 4.7 and adds a 'default' fallbacks mode
From 24 July 2026, speed: 'fast' on Opus 4.7 returns a hard 400 error. Here's what to fix and what the new fallbacks default mode gives you.
Claude Opus 4.1 is retired: what breaks on 5 August 2026 and how to fix it
The claude-opus-4-1-20250805 model ID retired on 5 August 2026. API calls to it now return a hard 404. Here is what to do.
GPT-5.4 and GPT-5.4 mini retire from Codex on 31 August 2026 for ChatGPT users
OpenAI is retiring GPT-5.4 and GPT-5.4 mini from Codex for ChatGPT-authenticated users on 31 August 2026. Here's what to do before the deadline.
Claude Opus 4.1 retires on 5 August 2026: migrate to Opus 4.8 now
The claude-opus-4-1-20250805 model ID stops working on 5 August 2026. Here's what to change and why Opus 4.8 is the right target.
OpenAI Assistants API is permanently removed on 26 August 2026: here's what you need to do
OpenAI's Assistants API is gone on 26 August 2026. This is a full architectural migration to the Responses API, not a quick endpoint swap.
Anthropic is retiring the legacy Claude Workbench and three experimental prompt API endpoints on 17 August 2026
The legacy Workbench and three /v1/experimental/ prompt endpoints shut down 17 August 2026. Here's what to export and what replaces them.
Imagen 4 endpoints shut down on 17 August 2026: and the migration is more than a model rename
Imagen 4 model endpoints hard-shut-down 17 August 2026. Migration means switching method, model name, and response parsing.
Anthropic is retiring Claude Opus 4.1 on August 5, 2026 — here's what developers need to do
Anthropic has deprecated claude-opus-4-1-20250805 with a retirement date of August 5, 2026. Opus 4.8 is the recommended replacement.
OpenAI cuts GPT-5.6 Luna pricing by 80% and frames it as the start of something bigger
OpenAI drops Luna API prices to $0.20/$1.20 per million tokens and trims Terra by 20%, calling it the beginning of an 'abundance flywheel' strategy.
Claude Sonnet 4 and Opus 4 are gone from the API — here's what to do
As of June 15, 2026, claude-sonnet-4-20250514 and claude-opus-4-20250514 return errors. Migrate to Sonnet 4.6 and Opus 4.8.
Anthropic Extends Claude Code Usage Boost to August 19 — And Sonnet 5 API Pricing Jumps 50% on September 1
Claude Code Pro/Max limits stay 50% higher through August 19, 2026. Sonnet 5 API intro pricing ends August 31 — and a tokenizer change makes the real cost rise bigger than it looks.
OpenAI's Secure MCP Tunnel lets private servers talk to ChatGPT without opening your firewall
OpenAI's GA Secure MCP Tunnel uses an outbound-only tunnel-client daemon so private MCP servers can serve ChatGPT, Codex, and the Responses API with no inbound firewall rules.
Google is shutting down its Gemini image preview models on June 25 — here's how to migrate
Gemini's preview image generation models are deprecated with a hard shutdown on June 25, 2026. Here's what to change and when.
Claude Code Artifacts can now pull live data through MCP connectors every time someone opens them
Claude Code Artifacts gain live MCP connector data, public sharing links, editor roles, and Claude Tag integration — here's what changed and what it means.
MCP 2026-07-28: Stateless Core, Hardened Auth, and Official Extensions Land Across Claude
The fifth MCP spec drops stateful sessions for a request/response core, hardens OAuth/OIDC auth, and graduates MCP Apps and Tasks as versioned extensions.
Claude Code v2.1.178: Precise Tool Permissions, Smarter Config Resolution, and Safer Sub-Agents
Claude Code's latest release adds parameter-level permission syntax, proximity-based .claude/ directory resolution, and pre-launch safety screening for sub-agents.
GitHub Copilot CLI v1.0.72 & v1.0.73: Critical Infinite-Loop Fix and Sandbox Security Tightening
Two back-to-back Copilot CLI releases fix a dangerous agentStop infinite-loop bug, tighten macOS sandbox defaults, and patch Anthropic subagent reliability.
claude-mythos-preview Is Deprecated — But Its Replacement Is Currently Unavailable
Anthropic has formally deprecated claude-mythos-preview with a June 30 2026 retirement date, directing developers to migrate to claude-mythos-5 — which is currently suspended.
Anthropic pauses its Agent SDK billing change on the day it was supposed to launch
Anthropic pulled back its planned Agent SDK credit separation on June 15, the day it was set to go live, saying it will rework the plan before any future change.
Claude Agent SDK Billing Splits on June 15: What the New Credit Pool Means for Your Plan
From June 15, Claude Agent SDK, claude -p, GitHub Actions, and third-party agents draw from a separate monthly credit, not your subscription quota.
Claude Code v2.1.169: Safe Mode, /cd Command, and a Pile of Bug Fixes
Claude Code v2.1.169 adds --safe-mode for clean troubleshooting sessions, a /cd command that preserves prompt cache, and fixes for Windows, background agents, and enterprise MCP policies.
Claude for Chrome is now generally available: what the browser extension means for your dev workflow
Anthropic's Claude for Chrome extension has exited preview and is now generally available to all direct paid plan users, bringing browser automation into Claude Code.
OpenAI's GPT-Realtime-2.1 Brings Better Reasoning and 25% Lower Latency to Voice Agents
OpenAI ships gpt-realtime-2.1 and gpt-realtime-2.1-mini with improved reasoning, noise handling, and a 25%+ p95 latency cut across all Realtime voice models.
Google is deprecating Veo 2 and Veo 3 on the Gemini API — here's what you need to do before June 30, 2026
Veo 2 and Veo 3 model IDs on the Gemini API are being shut down on June 30, 2026. Migrate to Veo 3.1 Preview or the Enterprise GA models now.
Google Lyria 3 Pro is now available on Vertex AI — here's what developers get
Google has opened Lyria 3 Pro and Lyria 3 Clip to enterprise developers via Vertex AI, marking the first public API access to the Lyria 3 model family.
Codex CLI v0.139.0: Code Mode Can Now Search the Web Mid-Task, and Complex Tool Schemas Finally Stay Intact
Codex CLI v0.139.0 lets code mode call web search directly, including from nested JS tool calls, and fixes oneOf/allOf schema preservation for MCP tools.
Gemini Code Assist and Gemini CLI are shutting down for consumer tiers on June 18, 2026 — here's how to migrate to Antigravity
Google is retiring Gemini Code Assist IDE extensions and Gemini CLI for free, Pro, and Ultra users on June 18, 2026. Migration to Antigravity CLI is required.
Codex gets Chrome DevTools Protocol access in new Developer Mode
Codex's new Developer mode gives the agent controlled CDP access to profile JavaScript, inspect network traffic, and debug live browser state.
Codex now imports your Claude Code setup — and it's built right into onboarding
OpenAI's latest Codex update adds guided migration from Claude Code and Claude Cowork, plus a revamped plugins screen with filters and keyboard navigation.
Anthropic adds an observability dashboard and in-app submission flow for Claude MCP connector owners
Claude's new public-beta dashboard gives MCP connector owners usage metrics, error diagnostics, and latency data — plus a direct submission flow to the connectors directory.
Microsoft Work IQ API is now generally available: what it does, what it costs, and what you need to do
Microsoft's Work IQ API reached GA on June 16, bringing an agent-ready intelligence layer for Microsoft 365 with consumption-based Copilot Credits billing.
Google Extends Gemini 2.5 Retirement on Vertex AI to October 2026
Google has pushed the Vertex AI retirement date for Gemini 2.5 Pro, Flash, and Flash-Lite to October 16, 2026, giving developers more time to migrate to Gemini 3.x.
ClaudeForFoundationModels: Anthropic's Swift package brings Claude into Apple's Foundation Models framework
Anthropic's new Swift package lets iOS/macOS 27 developers use Claude as a drop-in server-side model via Apple's LanguageModelSession API.
Gemini Interactions API: The June 8 Hard Removal Is Done — Here's What Breaks and How to Fix It
The legacy Gemini Interactions API outputs schema was permanently removed on June 8, 2026. Here's what changed, what's broken, and how to migrate.
Claude Code Gets Push Notifications, Fullscreen TUI, and Smarter Session Resume
Five focused updates to Claude Code: mobile push notifications, /tui fullscreen mode, PR URL resume, Bedrock tier control, and project purge.
Codex CLI Gets Session Archiving, Clickable Terminal Links, and Safer Remote Control
The latest Codex CLI update adds session archiving, OSC 8 hyperlinks in TUI markdown, richer MCP status, and short-lived WebSocket tokens for remote control.
Gemini Image Models Hit GA: What the Flash and Pro Releases Mean for Developers
Google's gemini-3.1-flash-image and gemini-3-pro-image are now generally available, with video-to-image generation added and preview models shutting down June 25.
Anthropic Claude API: Zero-Cost Refusals and a Smarter Advisor Tool for Agentic Pipelines
Anthropic now bills zero for API refusals with no output, and the advisor tool gets a max_tokens cap to control cost and latency in agentic workloads.
Claude Code v2.1.160: Faster auto mode, fewer CI headaches, and a raft of bug fixes
Claude Code v2.1.160 cuts auto mode classifier latency, fixes Bedrock/Vertex/Foundry CI failures, and resolves Bazel, OneDrive, CJK, and voice mode bugs.
Claude Code v2.1.163: Version Guardrails, Plugin Management, and a Sweep of Windows Fixes
Claude Code's latest release adds enterprise version enforcement, a /plugin list command, hook improvements, and fixes a pile of Windows and terminal rendering issues.
Google Gemini API now supports event-driven webhooks — no more polling for batch jobs
Google's Gemini API now pushes notifications when batch jobs and long-running operations finish, eliminating the need to poll for status.
Claude Code: 'workflow' renamed to 'ultracode', parallel Bash bug fixed, and OTEL team-level metrics added
Claude Code renames its dynamic-workflow trigger to 'ultracode', fixes a Bash parallel batch bug, tidies the MCP panel, and adds OTEL resource-attribute labels.
Claude Code Now Auto-Loads Plugins from Local Directories — No Marketplace Required
Claude Code gains filesystem-first plugin loading from .claude/skills, a scaffolding command, autocomplete, and hot-reload — no marketplace needed.
Microsoft Build 2026: Windows Agent Framework Goes Open Source, Project Polaris Takes Aim at GitHub Copilot's Future
Microsoft open-sourced its Windows Agent Framework, unveiled Project Polaris to replace GPT-4 Turbo in Copilot, and shipped Copilot Workspace as GA at Build 2026.
OpenAI Container Sessions Now Billed Per Minute — Short Sessions Get Cheaper from June 2
OpenAI switches container billing to per-minute with a 5-minute minimum from June 2, 2026, cutting costs for sessions under 20 minutes.
GitHub Copilot Now Bills by Token: What the Switch to AI Credits Means for Your Workflow
GitHub Copilot replaced flat premium request units with token-based AI Credits on June 1, 2026. Here's what changed and who it affects most.
Anthropic Acquires Stainless: What It Means for Developers Building on Claude
Anthropic has acquired Stainless, the startup behind every official Claude SDK and MCP server generator, in a deal reportedly worth over $300M.
OpenAI launches GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper in its API
OpenAI releases three purpose-built voice models in its Realtime API, bringing GPT-5-class reasoning, live translation, and streaming transcription to developers.
Gemini API File Search now handles images, custom metadata, and page-level citations
Google's Gemini API File Search gains multimodal support, metadata filtering, and page-level citations, making verifiable RAG practical for real-world mixed content.